The 26th European Conference on Artificial Intelligence (ECAI 2023) took place from 30 September – 4 October in Krakow, Poland. On the final day of the conference, the outstanding paper awards were announced. There were two winners in the ECAI 2023 Outstanding Paper category, and one winner in the Outstanding Paper for AI in Social Good category. Abstract: Learning effective strategies in sparse reward tasks is one of the fundamental challenges in reinforcement learning. This becomes extremely difficult in multi-agent environments, as the concurrent learning of multiple agents induces the non-stationarity problem and sharply increased joint state space.

Large Language Models (LLMs) are quickly becoming ubiquitous, but the implications for social science research are not yet well understood. This paper asks whether LLMs can help us analyse large-N qualitative data from open-ended interviews, with an application to transcripts of interviews with Rohingya refugees in Cox's Bazaar, Bangladesh. We find that a great deal of caution is needed in using LLMs to annotate text as there is a risk of introducing biases that can lead to misleading inferences. We here mean bias in the technical sense, that the errors that LLMs make in annotating interview transcripts are not random with respect to the characteristics of the interview subjects. Training simpler supervised models on high-quality human annotations with flexible coding leads to less measurement error and bias than LLM annotations. Therefore, given that some high quality annotations are necessary in order to asses whether an LLM introduces bias, we argue that it is probably preferable to train a bespoke model on these annotations than it is to use an LLM for annotation.

Rap legend Tupac Shakur, soulful English singer-songwriter Amy Winehouse and many other beloved, 'once in a lifetime' talents have been tragically robbed of a full lifetime to share their gifts with the world. So we put the image-making artificial intelligence (AI) Midjourney to work to help imagine what these stars might have looked like at age 80. The results were unusual and uncanny, as might be expected of a machine manifesting snaps from an alternate dimension of what could have been. Scroll down to see if you recognize these famous figures in their AI-generated old age. The results might surprise you.

When I spoke to my phone, my face appeared on the screen, and I said, 'Hi, my name is Robert, and I'm looking forward to telling you about my life.' I was talking to an AI avatar of myself, designed to allow people to'live on' after death so that relatives can talk to them and learn about their lives. My wife's reaction to my AI clone was absolute horror, as she simply said, 'My God, why?' The clone comes courtesy of a'digital afterlife' service, Hereafter.AI, part of a wave of AI-powered'grief tech' created by programmer James Vlahos after his father died of cancer in 2016. The service creates a'Legacy Avatar' that can live on after your death (Rob Waugh/Hereafter) Vlahos programmed a'Dadbot' while his father was still alive, recording his responses to questions - and Hereafter's service now uses AI to make it easier to interact. Science has unearthed several distinct patterns around when people tend to die.

Despite the remarkable advances in language modeling, current mainstream decoding methods still struggle to generate texts that align with human texts across different aspects. In particular, sampling-based methods produce less-repetitive texts which are often disjunctive in discourse, while search-based methods maintain topic coherence at the cost of increased repetition. Overall, these methods fall short in achieving holistic alignment across a broad range of aspects. In this work, we frame decoding from a language model as an optimization problem with the goal of strictly matching the expected performance with human texts measured by multiple metrics of desired aspects simultaneously. The resulting decoding distribution enjoys an analytical solution that scales the input language model distribution via a sequence-level energy function defined by these metrics. And most importantly, we prove that this induced distribution is guaranteed to improve the perplexity on human texts, which suggests a better approximation to the underlying distribution of human texts. To facilitate tractable sampling from this globally normalized distribution, we adopt the Sampling-Importance-Resampling technique. Experiments on various domains and model scales demonstrate the superiority of our method in metrics alignment with human texts and human evaluation over strong baselines.

Multivariate networks are commonly found in real-world data-driven applications. Uncovering and understanding the relations of interest in multivariate networks is not a trivial task. This paper presents a visual analytics workflow for studying multivariate networks to extract associations between different structural and semantic characteristics of the networks (e.g., what are the combinations of attributes largely relating to the density of a social network?). The workflow consists of a neural-network-based learning phase to classify the data based on the chosen input and output attributes, a dimensionality reduction and optimization phase to produce a simplified set of results for examination, and finally an interpreting phase conducted by the user through an interactive visualization interface. A key part of our design is a composite variable construction step that remodels nonlinear features obtained by neural networks into linear features that are intuitive to interpret. We demonstrate the capabilities of this workflow with multiple case studies on networks derived from social media usage and also evaluate the workflow through an expert interview.

We are in the midst of an unprecedented, intergenerational phone-game renaissance. Wordle has become a pillar of the New York Times brand, newspapers everywhere are resurrecting their crossword backpage, and Words With Friends has essentially transformed into a dating app. These games are designed to be approachably mainstream--every English speaker alive can deduce a five-letter word with six chances--but unfortunately, I am a man of unconventional taste. If I'm going to entertain a daily dose of potpourri, I need something weirder, more challenging, and better suited for the precise category of useless knowledge that occupies my brain. That's why the sports-trivia game Immaculate Grid has become a fixture of my morning routine.

Recent advancements in artificial intelligence (AI) are fundamentally reshaping computing, with large language models (LLMs) now effectively being able to generate and interpret source code and natural language instructions. These emergent capabilities have sparked urgent questions in the computing education community around how educators should adapt their pedagogy to address the challenges and to leverage the opportunities presented by this new technology. In this working group report, we undertake a comprehensive exploration of LLMs in the context of computing education and make five significant contributions. First, we provide a detailed review of the literature on LLMs in computing education and synthesise findings from 71 primary articles. Second, we report the findings of a survey of computing students and instructors from across 20 countries, capturing prevailing attitudes towards LLMs and their use in computing education contexts. Third, to understand how pedagogy is already changing, we offer insights collected from in-depth interviews with 22 computing educators from five continents who have already adapted their curricula and assessments. Fourth, we use the ACM Code of Ethics to frame a discussion of ethical issues raised by the use of large language models in computing education, and we provide concrete advice for policy makers, educators, and students. Finally, we benchmark the performance of LLMs on various computing education datasets, and highlight the extent to which the capabilities of current models are rapidly improving. Our aim is that this report will serve as a focal point for both researchers and practitioners who are exploring, adapting, using, and evaluating LLMs and LLM-based tools in computing classrooms.

The advent of Large Language Models (LLMs) has paved the way for complex tasks such as role-playing, which enhances user interactions by enabling models to imitate various characters. However, the closed-source nature of state-of-the-art LLMs and their general-purpose training limit role-playing optimization. In this paper, we introduce RoleLLM, a framework to benchmark, elicit, and enhance role-playing abilities in LLMs. RoleLLM comprises four stages: (1) Role Profile Construction for 100 roles; (2) Context-Based Instruction Generation (Context-Instruct) for role-specific knowledge extraction; (3) Role Prompting using GPT (RoleGPT) for speaking style imitation; and (4) Role-Conditioned Instruction Tuning (RoCIT) for fine-tuning open-source models along with role customization. By Context-Instruct and RoleGPT, we create RoleBench, the first systematic and fine-grained character-level benchmark dataset for role-playing with 168,093 samples. Moreover, RoCIT on RoleBench yields RoleLLaMA (English) and RoleGLM (Chinese), significantly enhancing role-playing abilities and even achieving comparable results with RoleGPT (using GPT-4).

Large language models (large LMs) are susceptible to producing text that contains hallucinated content. An important instance of this problem is self-contradiction, where the LM generates two contradictory sentences within the same context. In this work, we present a comprehensive investigation into self-contradiction for various instruction-tuned LMs, covering evaluation, detection, and mitigation. Our analysis reveals the prevalence of self-contradictions when LMs generate text for open-domain topics, e.g., in 17.7% of all sentences produced by ChatGPT. Self-contradiction also complements retrieval-based methods, as a large portion of them (e.g., 35.8% for ChatGPT) cannot be verified using Wikipedia. We then propose a novel prompting-based framework designed to effectively detect and mitigate self-contradictions. Our detector achieves high accuracy, e.g., around 80% F1 score when prompting ChatGPT. The mitigation algorithm iteratively refines the generated text to remove contradictory information while preserving text fluency and informativeness. Importantly, our entire framework is applicable to black-box LMs and does not require external grounded knowledge. Our approach is practically effective and has been released as a push-button tool to benefit the public, available at https://chatprotect.ai/.